WO2014027714A1 - Système et procédé de détection de changement d'itinéraire au moyen d'informations de reconnaissance d'image - Google Patents

Système et procédé de détection de changement d'itinéraire au moyen d'informations de reconnaissance d'image Download PDF

Info

Publication number
WO2014027714A1
WO2014027714A1 PCT/KR2012/007169 KR2012007169W WO2014027714A1 WO 2014027714 A1 WO2014027714 A1 WO 2014027714A1 KR 2012007169 W KR2012007169 W KR 2012007169W WO 2014027714 A1 WO2014027714 A1 WO 2014027714A1
Authority
WO
WIPO (PCT)
Prior art keywords
lane
information
image recognition
route
module
Prior art date
Application number
PCT/KR2012/007169
Other languages
English (en)
Korean (ko)
Inventor
박광일
임상묵
김진혁
Original Assignee
주식회사 피엘케이 테크놀로지
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 주식회사 피엘케이 테크놀로지 filed Critical 주식회사 피엘케이 테크놀로지
Priority to US13/984,695 priority Critical patent/US9070022B2/en
Priority to EP12866983.5A priority patent/EP2889198A4/fr
Publication of WO2014027714A1 publication Critical patent/WO2014027714A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3602—Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/06—Road conditions
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42—Determining position
    • G01S19/48—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system
    • G01S19/485—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system whereby the further system is an optical system or imaging system
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3626—Details of the output of route guidance instructions
    • G01C21/3658—Lane guidance
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42—Determining position
    • G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/09626—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages where the origin of the information is within the own vehicle, e.g. a local storage device, digital map

Definitions

  • the present invention relates to an assistive technology for safe driving of a vehicle, and relates to a system and a method for determining a route change of a vehicle using image recognition information.
  • an electronic device such as a navigation device guides a destination when the vehicle is driven by using GPS location information and various sensors based on road map information, or re-detects and guides the destination when the vehicle deviates from the route to the destination.
  • the GPS (Global Positioning System) device has a positional accuracy of 20 to 30m.
  • the GPS device may not recognize the correct driving lane, and thus, even if the user departs from the route to the destination, immediate guidance is impossible. Therefore, if a wrong route is selected and deviated from the route to the destination, there is a problem of returning after a considerable distance or detouring to another route.
  • DGPS differential global positioning system
  • the DGPS device is very expensive equipment, the price of the vehicle is dramatically increased when mounted in the vehicle.
  • the autonomous driving system using the DGPS device is inherently limited to be mounted on a vehicle and spread.
  • the present invention provides a route change determination system and method using image recognition information capable of determining a change in a driving route by enabling the extraction of high-precision position information similar to a high-precision DGPS apparatus while using a GPS device of low precision. to provide.
  • the present invention also provides a route change determination system and method using image recognition information capable of determining a change in a driving route using lane information, image recognition information, and section information linked to a GPS device.
  • Path change determination system using the image recognition information of the present invention, GPS module; An image recognition module having a lane recognition function; A road map storage module configured to store route changeable section information and road map information capable of changing a route of the vehicle; A road map receiving module to receive the road map information; And an operation processing module that determines whether to change the route based on the lane recognition information recognized by the image recognition module and the route changeable section information.
  • the road map information stored in the road map storage module may include lane characteristic information
  • the calculation processing module may further include an information matching unit configured to calculate a driving lane by matching the lane recognition information with the lane characteristic information. If it is recognized by the image recognition module that a part of the vehicle is located on the route change lane, the information matching unit determines that the lane change for the route change is in progress.
  • the road map information stored in the road map storage module may include lane characteristic information
  • the calculation processing module may further include an information matching unit configured to calculate a driving lane by matching the lane recognition information with the lane characteristic information. If it is recognized by the image recognition module that all of the vehicle is out of the route change lane, the information matching unit determines that the lane change for the route change is determined.
  • the road map information stored in the road map storage module may include lane characteristic information, and the calculation processing module may further include an information matching unit configured to calculate a driving lane by matching the lane recognition information with the lane characteristic information. If it is detected from the image recognized by the image recognition module that the vehicle has entered from the "route changeable section" to the "route change section", it is determined that the route change is completed.
  • the route changeable section included in the route changeable section information is set when the ongoing route is in contact with the existing route, a new route is generated from the ongoing route, or the ongoing route itself is divided into two or more. do.
  • the calculation processing module determines that the vehicle travels along a path connected to the left lane.
  • the offset of the left lane obtained from the image recognition module is kept constant, and the right lane disappears from the image obtained from the image recognition module.
  • the calculation processing module determines that the vehicle travels along a path connected to the left lane.
  • the apparatus may further include a lane change tracking unit configured to calculate a driving lane by tracking a lane change history of the vehicle in a state where it is impossible to calculate a driving lane by the information matching unit.
  • a lane change tracking unit configured to calculate a driving lane by tracking a lane change history of the vehicle in a state where it is impossible to calculate a driving lane by the information matching unit.
  • the calculation processing module may further include a positioning correction unit configured to correct the road positioning by calculating an offset of the left lane of the current driving lane from the image recognition information.
  • the positioning correction unit corrects road positioning by adding up the sum of the road widths of the left lanes and the offset included in the lane characteristic information.
  • the calculation processing module may further include an end estimator for estimating a road end by calculating a head angle formed by a lane and a traveling direction from the image recognition information when the reception signal of the GPS module is cut off.
  • the route change determination method using the image recognition information of the present invention (a) a driving lane operation step of calculating the driving lane by matching the lane recognition information recognized by the image recognition module with the lane characteristic information of the road map information; And (b) if it is recognized by the image recognition module that a part of the vehicle is located on a route change lane, the operation processing module includes determining that a lane change for a route change is in progress.
  • the operation processing module further comprises the step of determining that the lane change for the path change is determined.
  • the method may further include determining that the path change is completed when it is detected from the image recognized by the image recognition module that the vehicle enters the “no path change section” from the “route change section”.
  • the road positioning correction step corrects road positioning by adding up the sum of the road widths of the left lanes and the offset included in the lane characteristic information.
  • the present invention it is possible to extract high-precision location information similar to a high-precision DGPS device while using a low-precision GPS device, to determine a change in a driving route, and to detect lane information and images linked with the GPS device.
  • the change of the driving route may be determined using the recognition information and the section information.
  • FIG. 1 is a block diagram of a GPS correction system according to an embodiment of the present invention.
  • 2a and 2b is a screen shot in the image recognition module
  • FIG. 3 is a lane characteristic information table according to an embodiment of the present invention.
  • 5 to 8 is an exemplary view of a driving lane calculation according to an embodiment of the present invention.
  • FIG. 10 is a lane width information table according to an embodiment of the present invention.
  • FIG. 12 is a diagram illustrating a final estimation according to an embodiment of the present invention.
  • FIG. 14 is a view illustrating a route change determination for each section according to an embodiment of the present invention.
  • 15 is an exemplary view of a state of rerouting according to an embodiment of the present invention.
  • 16 is a diagram illustrating a lane change and route determination determination method according to another embodiment of the present invention.
  • ⁇ means a unit for processing at least one function or operation, which may be implemented by hardware or software or a combination of hardware and software. Can be.
  • a part is electrically connected to another part, this includes not only the case where it is directly connected, but also the case where it is connected through the other structure in the middle.
  • 'Lane' means a line drawn by a solid line or a dotted line on both sides of the lane in which the vehicle is traveling
  • 'lane' means a road in which the vehicle travels between both lanes
  • 'route' means a lane by changing lanes It refers to a set of one or more lanes which can be moved between two roads and the vehicle can reach the same destination at the starting point regardless of which lanes the vehicle travels along.
  • the GPS correction system using the image recognition information of the present invention communicates with a GPS module 210 and an image recognition module 220 mounted on a vehicle to calculate a current driving lane information of a vehicle ( 100).
  • the road map storage module 230 for storing road map information including lane characteristic information, or the road map receiving module 240 for receiving such road map information may be selectively selected. It can be provided.
  • the road map storage module 230 and the road map receiving module 240 may be provided together.
  • the road map storage module 230 may include a flash memory type, a hard disk type, a multimedia card micro type, and a card type memory (for example, SD or XD). Memory, etc.), random access memory (RAM), static random access memory (SRAM), readonly memory (ROM), electrically erasable programmable readonly memory (EEPROM), programmable readonly memory (PROM), magnetic memory, magnetic disk It may include at least one type of storage medium of the optical disk.
  • RAM random access memory
  • SRAM static random access memory
  • ROM readonly memory
  • EEPROM electrically erasable programmable readonly memory
  • PROM programmable readonly memory
  • magnetic memory magnetic disk It may include at least one type of storage medium of the optical disk.
  • the operation processing module 100 and the image recognition module 220 are illustrated separately.
  • the image recognition module 220 in the navigation may include the calculation processing module 100, or the image recognition module 220 and the calculation processing module 100 may be provided together in the autonomous driving system 250.
  • the two modules consist of one processor and may be executed separately by software or by separate execution routines. That is, the operation processing module 100, the image recognition module 220, and other components are merely functionally separated and may be realized on the same hardware.
  • the GPS module 210 does not require high precision.
  • the arithmetic processing module 100 of the present invention converts the position information obtained from the GPS module 210, which is usually provided at low cost, into image having high precision by correcting the image information using image recognition information.
  • the GPS module 210 may obtain location data through a global navigation satellite system (GNSS).
  • GNSS refers to a navigation system that can calculate the position of a receiver terminal using radio signals received from satellites.
  • Specific examples of GNSS include Global Positioning System (GPS), Galileo, Global Orbiting Navigational Satellite System (GLONASS), COMPASS, Indian Regional Navigational Satellite System (IRNS), and Quasi-Zenith Satellite System (QZSS), depending on the operating entity. Can be.
  • the calculation processing module 100 calculates driving lane information and transmits high-precision position information to the autonomous driving system 250.
  • Device-to-device communication may be made through a CAN (Car Area Network).
  • the device-to-device communication according to another embodiment of the present invention is also possible short-range wireless communication method, Bluetooth (Bluetooth), RFID (Radio Frequency Identification), Infrared Data Association (UWB), UWB (Ultra WideBand), ZigBee ( ZigBee) and the like.
  • the operation processing module 100 includes at least one processor.
  • the arithmetic processing module 100 includes an information matching unit 110, a lane change tracking unit 120, a positioning correction unit 130, and a longitudinal estimation unit 140.
  • Each unit may be configured as an independent processor in the arithmetic processing module 100 or a subroutine programmed in one processor. In addition, some components may optionally be used.
  • FIGS. 2A and 2B are images captured by a camera mounted on a vehicle while driving a vehicle.
  • Figure 2a is a photograph of the national highway 1 lane
  • Figure 2b is a photograph of the highway two lanes.
  • the left lane of the driving lane of the vehicle represents a center line with a yellow double solid line
  • the right lane is a solid white line.
  • the left lane of the driving lane is a blue double solid line indicating a bus-only lane
  • the right lane is a white dotted line. In this way, the lane expresses various information according to the position of the lane.
  • the lanes when there are many lanes, most lanes are indicated by a dotted white line, and in the case of a bus-only lane, the lanes may be located at the right lane instead of the left lane, so that the image captured by the camera may be analyzed by the image recognition module 220. It is impossible to recognize the driving lane accurately just by doing so.
  • the operation processing module 100 basically calculates the driving lane by matching the lane recognition information recognized by the image recognition module 220 with the road map information.
  • the road map information is stored in the road map storage module 230.
  • the road map receiving module 240 may receive road map information by communicating with an external device.
  • Road map information according to an embodiment of the present invention may be road map information provided by the vehicle safety driving assistance device.
  • the road map information according to another embodiment of the present invention may be dedicated road map information provided for GPS correction.
  • the road map information includes lane characteristic information as shown in FIG. 3.
  • Lane characteristic information means information on a lane corresponding to the current position measured by the GPS module 210. Referring to FIG. 3, the lane characteristic information includes whether there is a double line, color information of a lane, and shape information of a lane (eg, solid line, dotted line, etc.).
  • lane 3 is a lane characteristic information table according to an embodiment of the present invention, where the lane number '0' means a center line, and the double line is a yellow solid line.
  • One lane is a double line and a solid blue line means a bus-only lane.
  • a primary lane is formed between the center line and the primary lane.
  • Lanes 2 through 4 are white dotted lines, and lanes 5 are white solid lines.
  • lane recognition information as shown in FIG. 4 may be obtained.
  • the lane number '0' means the left lane and '1' means the right lane.
  • the left lane is an overlapping line and a solid blue line.
  • the right lane is a dashed white line.
  • the information matching unit 110 of the arithmetic processing module 100 matches the lane recognition information recognized by the image recognition module 220 with the lane characteristic information.
  • lane numbers 0 and 1 of the lane recognition information perfectly and uniquely match lane numbers 1 and 2 of the lane characteristic information.
  • the information matching unit 110 may determine that the current driving lane is the second lane.
  • the GPS module 210 of low precision is difficult to recognize the correct driving lane, but through this information matching it is possible to accurately calculate the current driving lane of the vehicle.
  • the driving lane may be calculated even when the lane recognition information and the lane characteristic information partially match.
  • the lane information recognized by the image recognition module 220 may be recognized as a single line.
  • the lane recognition information may recognize the left lane as a single line and a blue solid line, and the right lane as a white dotted line.
  • the information matching unit 110 performs information matching as shown in FIG. 6.
  • the left lane partially matches the first lane of the lane characteristic information, but the right lane perfectly matches.
  • the left and right lanes of the lane recognition information do not match with other lanes. That is, the lane recognition information is uniquely matched when the left lane is the first lane and the right lane is the second lane. Therefore, even in this case, the information matching unit 110 may determine that the current driving lane is the second lane.
  • the lane recognition information may be information about four lanes.
  • the image recognition module 220 may recognize other lane information in addition to both lane information on the currently driving lane.
  • a side line may not be recognized correctly.
  • the information matching unit 110 performs information matching as shown in FIG. 7.
  • the four lane information of the lane recognition information, together with some partial matching and partial perfect matching, are shown together, but are uniquely matched with the lane characteristic information from the center line to the three lanes.
  • the driving lane can be accurately calculated by matching the lane recognition information with the lane characteristic information.
  • the lane recognition information and the lane characteristic information exactly match each other as in FIG. 8, a case in which the lane recognition information and the lane characteristic information do not coincide alone may occur. If both the left lane information and the right lane information of the lane recognition information show a white dotted line, this perfectly matches both the second and third lanes, or the three and fourth lanes when matching with the lane characteristic information. In this case, the driving lane cannot be completely calculated only by the information matching unit 110.
  • the lane change tracking unit 120 of FIG. 1 tracks the most recent information matching result. For example, if the most recent information matching result is determined by calculating the driving lane as the second lane, the lane change history is then reviewed. Since the lane change history can be checked in the image recognition module 220, the driving lane can be tracked by substituting the lane change time.
  • the driving lane of the current vehicle can be determined as the third lane. have.
  • the latest information matching result confirming the lane as the driving lane if the lane change to the right lane is performed, 1 is added to the driving lane and if the lane change to the left lane is performed, 1 is reduced to the driving lane. In this manner, the driving lane may be tracked and calculated until the next driving lane is determined.
  • the current vehicle position may be limited and estimated within the driving lane. Since the width of the road is usually about 3m, accurate position estimation with very small error is possible.
  • the path change determination system and method of the present invention can calculate more precise position information by using the positioning corrector 130 and the end estimator 140 shown in FIG. 1.
  • the operation processing module 100 calculates a driving lane by matching lane recognition information recognized by the image recognition module 220 with lane characteristic information of the road map information (ST110).
  • ST110 lane characteristic information of the road map information
  • Various examples of calculating the driving lane in the information matching unit 110 are as described above.
  • the lane change tracking unit 120 tracks the lane change history of the vehicle and corrects the driving lane (ST120).
  • the road side is corrected by calculating an offset for the left lane (ST130).
  • the lane characteristic information includes the width information of each lane. If the driving lane is determined as the second lane in step ST110 or ST120, the width from the center line to the left lane of the driving lane can be known from the sum of the road widths up to the second lane. In FIG. 10, the sum of road widths to the left lane is 6 m.
  • the distance between the left lane and the vehicle may be obtained from the image recognition module 220.
  • a particular point on the road is projected onto a point in the image through a camera transformation.
  • the camera conversion equation is determined by the camera's coordinate conversion model, the correction model, the focal length of the lens, the installation height of the camera, and the installation angle of the camera. If the camera inverse transformation is used in the lane recognized in the image, an offset between the lane and the vehicle can be obtained.
  • x and y are coordinate values on the screen
  • X and Z are coordinate values on the road
  • ⁇ is the focal length of the lens
  • ⁇ is the camera installation angle
  • h is the camera installation height.
  • the positioning correction unit 130 corrects road positioning by adding up the sum of the road widths of the left lanes of the current driving lane and an offset obtained by using the above formula, and thus has a very low error compared to the simple driving lane information. High precision positioning can be obtained. By correcting using the offset of the driving lane, the error is reduced to within several tens of centimeters.
  • the head angle between the lane and the traveling direction of the vehicle is calculated to estimate the longitudinal position (ST140).
  • the road direction refers to the displacement of the lane on the road map, and in the unmanned driving or navigation guidance, autonomous driving control or geographic guidance is performed according to the road direction. By the way, it is necessary to estimate the end point at the point where reception of the GPS module 110 is cut off, such as inside a tunnel.
  • the longitudinal estimation according to the prior art assumes that the driving speed is kept constant at the moment when GPS reception is cut off. However, this method causes an error in position estimation when traffic congestion occurs in a tunnel. Alternatively, displacements were corrected using inertial sensors, acceleration sensors, and gyro sensors. In this case, too, it is difficult to measure the relationship between the estimated displacement and the lane on the road map as an absolute displacement.
  • the road end is estimated using the image recognition information.
  • the terminal estimator 140 calculates a head angle between the lane and the traveling direction of the vehicle through image recognition of the front page at the moment when GPS reception is stopped.
  • the vehicle speed information is obtained from the ECU or the speed sensor of the vehicle.
  • the distance traveled in the lane direction during the measurement cycle can be obtained from Equation 3 below.
  • the moving direction coincides with the normal direction of the lane on the road map. As a result, the movement direction at the curved portion changes every moment.
  • ⁇ t is the amount of change in time
  • v is the speed of the vehicle
  • ⁇ is the head angle between the lane and the traveling direction of the vehicle.
  • Equation 3 By accumulating the value of Equation 3 for a certain time (for example, from the moment when GPS reception is lost to the time of recovery), the distance traveled along the longitudinal direction of the lane can be known. can do.
  • 13 is an exemplary view of changing the route for each section on the road according to an embodiment of the present invention.
  • the route according to the present invention is divided into 'routing impossible section' and 'route changing section' and is stored in the road map storage module 230.
  • 'No route changeable section' is a section that cannot be moved from the current route by a lane change until it leaves the section, and a 'path changeable section' is different from the route being driven by the lane change before leaving the section. It is a section that can be moved by a path. If there is no path change within a predetermined section, it does not correspond to a 'path changeable section'.
  • the 'routeable section' can be connected to either 'routeless section' or 'routeable section' before or after it, and 'routeable section' can be connected one after another. Referencing a 'routeable section' equally with the path after passing through the section and at least one route before passing the section corresponds to the naming of a conventional route.
  • new lanes may be created or destroyed within the 'path'. For example, even if a newly created lane leads to a lane that can be changed to another path in the future, such as a non-routing section II, it does not need to be considered separately until this becomes clear. It is sufficient to reflect in the lane information that lanes have been added as they move forward.
  • a path changeable section according to the present invention is set in the following case.
  • path change in FIG. 13 may be classified as follows.
  • path maintenance can be classified as follows.
  • 14A to 14F illustrate examples of route change determination for each section according to an embodiment of the present invention, in which individual sections of FIG. 13 are modeled for each section.
  • the arrow indicates the driving direction of the vehicle
  • the box on the left indicates the lane at the point of entry
  • the arrow pointing to the box indicates the path at the point of entry
  • the box on the right shows the lane at the point of entry.
  • the arrow indicates the path of entry. If the box indicating the lane is on the left side only, the lane is extinguished. If only on the right side, the box indicating the lane is generated.
  • the lane at the time of entry corresponding to the lane at the point of entry represents the lane following when the vehicle is driven without changing lanes despite the lane disappearing or created in the middle of the section, and the lane at the point of entry and the lane at the point of departure do not correspond. Indicates that a change can be made to move.
  • 'L' indicates the lane adjacent to the left side of the route, if there are multiple lanes, it is indicated by L1, L2, ..., etc.
  • 'R' indicates the lane adjacent to the right side of the route, and if there are multiple lanes R1, R2, ... are indicated.
  • FIG. 14A is a route change impossible section (I) in which the number of lanes at the time of entry and the number of lanes at the time of entry and exit cannot be changed
  • FIG. 14B shows that the number of lanes at the time of entry is greater than the number of lanes at the time of entry. It is still a non-changeable section (II) where the path cannot be changed
  • FIG. 14C is a changeable section (I) which can change the path to the path C on the left or the path D on the right
  • FIG. 14D is the path C on the left.
  • a route changeable section (II) capable of changing the route FIG.
  • FIG. 14E is a route changeable section (III) capable of changing the route because route A is divided into a route A and a route B, and FIG. 14F is the number of lanes at the time of entry. It is the section (III) where the route cannot be changed due to the same number of lanes.
  • FIG. 15 is a diagram illustrating a state of a route change according to an embodiment of the present invention, and may determine a route change intention, a route change progress, a route change decision, and a route change completion according to a current position of the vehicle.
  • the information matching unit 110 in the arithmetic processing module 100 when the offset of the path change lane obtained from the image recognition module 220 is reduced by more than a predetermined ratio with time. If it is determined that there is an intention of rerouting (1501), and the vehicle is recognized as being part of the vehicle by the image recognition module 220, it is determined that the lane change for rerouting is in progress (1502). If it is recognized by the recognition module 220 that all of the vehicle is out of the route change lane, it is determined that the lane change for the route change has been determined (1503), and the vehicle is determined from the image recognized by the image recognition module 220.
  • the route change lane means a lane for entering another path on the current path, for example, the leftmost lane, the rightmost lane, or the lane in which the ongoing path itself is divided.
  • the route change lane on the left means the lane between the "L" lane and the "1" lane.
  • the right path changing lane means the lane between the "4" lane and the "R" lane.
  • the information matching unit 110 in the arithmetic processing module 100 does not change the lane for changing the path, so that the lane changing for the path change even when the path at the time of entry is predicted. It is determined that this was determined.
  • FIG. 16 is a diagram illustrating a method for determining a lane change and a route determination according to another embodiment of the present invention, which may be used when a lane is partially erased or unclear and not recognized, or when the lane determines a lane change. Can be.
  • the information matching unit 110 in the arithmetic processing module 100 may have a left vehicle. It is determined that the vehicle will travel along the route connected to the lane.
  • the vehicle travels along the left lane 1601
  • the vehicle determines that the vehicle will travel along a path connected to the left lane.
  • the information matching unit 110 in the arithmetic processing module 100 indicates that the vehicle has a right lane 1605. It is determined that it will travel along the path connected to the).
  • the left lane offset and the right lane offset are distances to the left lane 1601 and the right lane 1605 around the virtual reference line 1603 in the center of the vehicle, respectively.
  • the route change determination system and method using the image recognition information of the present invention may specify (i) lane recognition information and lane characteristic information, and (ii) track lane changes to specify a driving lane. Further, (iii) the road position is corrected by calculating the offset of the left lane of the driving lane from the image recognition information, and (iv) the road angle is estimated by calculating the head angle from the image recognition information, whereby It can be specified precisely. Therefore, the change of the driving route can be determined, and the change of the driving route can be accurately determined using the lane information, the image recognition information, and the section-specific information linked to the GPS device.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Navigation (AREA)

Abstract

L'invention concerne un système et un procédé aptes à détecter, au moyen d'informations de reconnaissance d'image, des changements d'un itinéraire de déplacement en rendant possible l'extraction d'informations de position hautement précises similaires à celles d'un système DGPS de haute précision même lors de l'utilisation d'un système GPS de faible précision. Un système de détection de changements d'itinéraire au moyen d'informations de reconnaissance d'image selon la présente invention comprend : un module GPS ; un module de reconnaissance d'image ayant une fonction de reconnaissance de voie de circulation ; un module de stockage de carte routière pour stocker des informations de carte routière et des informations concernant des sections d'itinéraire pouvant être changées dans lesquelles un itinéraire de véhicule peut être changé ; un module de réception de carte routière pour recevoir les informations de carte routière ; et un module de traitement de calcul pour déterminer si un changement d'un itinéraire de véhicule existe ou non sur la base d'informations de reconnaissance de voie de circulation provenant du module de reconnaissance d'image et des informations concernant les sections d'itinéraire pouvant être changées.
PCT/KR2012/007169 2012-08-16 2012-09-06 Système et procédé de détection de changement d'itinéraire au moyen d'informations de reconnaissance d'image WO2014027714A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US13/984,695 US9070022B2 (en) 2012-08-16 2012-09-06 Route change determination system and method using image recognition information
EP12866983.5A EP2889198A4 (fr) 2012-08-16 2012-09-06 Système et procédé de détection de changement d'itinéraire au moyen d'informations de reconnaissance d'image

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2012-0089592 2012-08-16
KR1020120089592A KR101217594B1 (ko) 2012-08-16 2012-08-16 영상 인식 정보를 이용한 경로 변경 판정 시스템 및 방법

Publications (1)

Publication Number Publication Date
WO2014027714A1 true WO2014027714A1 (fr) 2014-02-20

Family

ID=47840958

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2012/007169 WO2014027714A1 (fr) 2012-08-16 2012-09-06 Système et procédé de détection de changement d'itinéraire au moyen d'informations de reconnaissance d'image

Country Status (3)

Country Link
EP (1) EP2889198A4 (fr)
KR (1) KR101217594B1 (fr)
WO (1) WO2014027714A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113074749A (zh) * 2021-06-07 2021-07-06 湖北亿咖通科技有限公司 一种路况检测和更新方法、电子设备和计算机可存储介质

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102018582B1 (ko) * 2013-12-31 2019-09-05 현대엠엔소프트 주식회사 고속화도로 내 본선과 램프 진출입로를 구분하여 교통정보를 수집하는 장치 및 방법
KR101573764B1 (ko) 2014-07-28 2015-12-02 현대모비스 주식회사 차량의 주행 차로 인식 시스템 및 방법
KR101704405B1 (ko) * 2016-03-31 2017-02-15 (주)와이파이브 차선 인식 시스템 및 방법
KR101659251B1 (ko) * 2016-04-19 2016-09-23 현대건설주식회사 주행 차로 정보 또는 도로 정보의 식별 시스템 및 이를 이용한 식별 방법
KR20180080391A (ko) * 2017-01-02 2018-07-12 주식회사 피엘케이 테크놀로지 V2x 통신을 이용한 무단 횡단 보행자의 사고 방지 시스템
KR102163774B1 (ko) * 2018-05-25 2020-10-08 (주)에이다스원 영상 인식 장치 및 그 방법
CN109800901A (zh) * 2018-12-07 2019-05-24 纳恩博（北京）科技有限公司 滑板车的调度方法、装置、存储介质及电子装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005265494A (ja) * 2004-03-17 2005-09-29 Hitachi Ltd 車両位置推定装置およびこれを用いた運転支援装置
JP2006023278A (ja) * 2004-06-07 2006-01-26 Nissan Motor Co Ltd 車載用ナビゲーション装置とこれに用いる車線位置推定装置
JP2006047291A (ja) * 2004-07-01 2006-02-16 Sanei Giken:Kk デジタルレーンマーク作成装置
JP2006300534A (ja) * 2005-04-15 2006-11-02 Auto Network Gijutsu Kenkyusho:Kk 車両周辺監視装置および運転支援装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4513740B2 (ja) * 2005-12-28 2010-07-28 アイシン・エィ・ダブリュ株式会社 経路案内システム及び経路案内方法
JP4446204B2 (ja) * 2007-10-30 2010-04-07 アイシン・エィ・ダブリュ株式会社 車両用ナビゲーション装置及び車両用ナビゲーションプログラム

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005265494A (ja) * 2004-03-17 2005-09-29 Hitachi Ltd 車両位置推定装置およびこれを用いた運転支援装置
JP2006023278A (ja) * 2004-06-07 2006-01-26 Nissan Motor Co Ltd 車載用ナビゲーション装置とこれに用いる車線位置推定装置
JP2006047291A (ja) * 2004-07-01 2006-02-16 Sanei Giken:Kk デジタルレーンマーク作成装置
JP2006300534A (ja) * 2005-04-15 2006-11-02 Auto Network Gijutsu Kenkyusho:Kk 車両周辺監視装置および運転支援装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP2889198A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113074749A (zh) * 2021-06-07 2021-07-06 湖北亿咖通科技有限公司 一种路况检测和更新方法、电子设备和计算机可存储介质
CN113074749B (zh) * 2021-06-07 2021-08-20 湖北亿咖通科技有限公司 一种路况检测和更新方法、电子设备和计算机可存储介质

Also Published As

Publication number Publication date
KR101217594B1 (ko) 2013-01-03
EP2889198A1 (fr) 2015-07-01
EP2889198A4 (fr) 2016-03-30

Similar Documents

Publication Publication Date Title
WO2014027718A1 (fr) Système de navigation qui détecte un changement d'itinéraire de véhicule
WO2014027714A1 (fr) Système et procédé de détection de changement d'itinéraire au moyen d'informations de reconnaissance d'image
KR101209062B1 (ko) 영상인식 정보를 이용한 ｇｐｓ 보정 시스템 및 방법
JP3436074B2 (ja) 車載ステレオカメラ
CN101424538B (zh) 车辆用导航装置以及车辆用导航方法
KR101919366B1 (ko) 차량 내부 네트워크 및 영상 센서를 이용한 차량 위치 인식 장치 및 그 방법
KR100873474B1 (ko) 영상상의 교통 시설물의 픽셀 사이즈 및 위치를 이용한차량 위치 추정 장치 및 그 방법
CN107836017B (zh) 信号机识别装置及信号机识别方法
US9070022B2 (en) Route change determination system and method using image recognition information
KR100224326B1 (ko) 차량용 네비게이션장치
EP2159541A1 (fr) Dispositif de navigation, procédé de navigation et programme de navigation
WO2021006441A1 (fr) Procédé de collecte d'informations de panneau de signalisation routière utilisant un système de cartographie mobile
US20140032100A1 (en) Gps correction system and method using image recognition information
WO2015147371A1 (fr) Dispositif et procédé de correction de position de véhicule, système de correction de position de véhicule à l'aide de celui-ci, et véhicule capable de fonctionnement automatique
WO2020159076A1 (fr) Dispositif et procédé d'estimation d'emplacement de point de repère, et support d'enregistrement lisible par ordinateur stockant un programme informatique programmé pour mettre en œuvre le procédé
CN102589560B (zh) 导航装置、导航方法及导航程序
CN110431609B (zh) 车辆位置推定装置
WO2021158062A1 (fr) Procédé de reconnaissance de position et système de reconnaissance de position pour véhicule
WO2018021870A1 (fr) Système de navigation et procédé de correction de localisation du système de navigation
JP2019120629A (ja) 位置計算装置、位置計算プログラム及び座標マーカ
WO2020180076A1 (fr) Appareil et procédé d'acquisition d'informations de correction de capteur de véhicule
JP2017032356A (ja) ステレオ画像処理装置
KR102407296B1 (ko) 관심지점 표시 장치 및 방법
JP2014145666A (ja) 走行案内システム、走行案内方法及びコンピュータプログラム
JP2008185506A (ja) ナビゲーション装置、ナビゲーション方法、および、自動車

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 2012866983

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 13984695

Country of ref document: US

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 12866983

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE